Blind Source Separation Based on a Single Observation

Damjan Zazula, Aleš Holobar

Abstract

This paper deals with a novel approach to the compound signal decomposition. It takes advantage of blind source separation using the algorithm for convolution kernel compensation (CKC). We derive a version which cope with compound signals, mixtures of several source contributions, even if only a single observation is available. Our novel approach detects and separates the triggering instants of all source symbols which contribute to the processed observation. The obtained decomposition is very robust and accurate. We experimented with synthetic signals having characteristics similar to the electrocardiographic (ECG) signals. Also at signal-to-noise ratios (SNRs) as low as 0 dB, the obtained average true positive statistics for the detected source- symbol triggerings was 98±1%, average false positive statistics 2±1%, and false negative statistics 3±2%.

References

  1. Zazula, D., Korže, D., Šoštaric, A., Korošec, D.: Study of Methods for Decomposition of Superimposed Signals with Application to Electromyograms. In: Pedotti et al. (eds.): Neuroprosthetics, Springer Verlag, Berlin (1996).
  2. Prakriya, S.: Eigenanalysis-based blind methods for identification, equalization, and inversion of linear time-invariant channels. IEEE Transactions on Signal Processing, Vol. 50, 7 (2002) 1525-1532.
  3. Cardoso, J. F.: Blind signal separation: statistical principles. Proceeding of the IEEE. Special issue on blind identification and estimation, Vol. 9, 10 (1998) 2009-2025.
  4. Tong, L., Liu, R.: Blind estimation of correlated source signals. In: Proc. Asilomar Conf. (1990) 161-164.
  5. Belouchrani, A., Meraim, K. A., Cardoso, J. F., Moulines, E.: A blind source separation technique based on second order statistics. IEEE Transactions on signal processing, Vol. 45, 2 (1997) 434-44.
  6. Pham, D. T., Cardoso, J. F.: Blind separation of instantaneous mixtures of non stationary sources. IEEE Transactions on Signal Processing, Vol. 49, 9 (2001) 1837-1848.
  7. Belouchrani, A., Moeness, A. G.: Blind source separation based on time-frequency signal representation. IEEE Transactions on Signal Processing, Vol. 46, 11 (1998).
  8. Holobar, A., Fevotte, C., Doncarli, C., Zazula, D.: Single autoterms selection for blind source separation in time-frequency plane. In: XI European Signal Processing Conference EUSIPCO 2002, Toulouse, France (2002) 4 pp.
  9. Nikias, C. L., Petropolu, A. P.: Higher-Order Spectra Analysis: A Nonlinear Signal Processing Framework. Prentice Hall signal processing series, Englewood Cliffs (1993).
  10. Zazula, D., Karlsson, S., Doncarli, C.: Advanced signal processing techniques. In R. Merletti, P. Parker (eds.), Electromyography: physiology, engineering, and noninvasive applications. John Wiley & Sons, Hoboken, NJ (2004) 259-304.
  11. Holobar, A., Zazula, D.: Correlation-based decomposition of surface electromyograms at low contraction forces. Med. biol. eng. comput., Vol. 42, 4 (2004) 487-495.
  12. Holobar, A., Zazula, D.: Correlation-based approach to multichannel blind deconvolution of binary sources. Submitted to IEEE Trans. on Sig. Proc.
  13. Kay, S. M.: Fundamentals of Statistical Signal Processing. Prentice-Hall International, London (1993).
Download


Paper Citation


in Harvard Style

Zazula D. and Holobar A. (2006). Blind Source Separation Based on a Single Observation . In Proceedings of the 2nd International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2006) ISBN 978-972-8865-67-2, pages 76-85. DOI: 10.5220/0001224100760085


in Bibtex Style

@conference{bpc06,
author={Damjan Zazula and Aleš Holobar},
title={Blind Source Separation Based on a Single Observation},
booktitle={Proceedings of the 2nd International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2006)},
year={2006},
pages={76-85},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001224100760085},
isbn={978-972-8865-67-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Workshop on Biosignal Processing and Classification - Volume 1: BPC, (ICINCO 2006)
TI - Blind Source Separation Based on a Single Observation
SN - 978-972-8865-67-2
AU - Zazula D.
AU - Holobar A.
PY - 2006
SP - 76
EP - 85
DO - 10.5220/0001224100760085